Rapid generation of three-dimensional characters
Aspects described herein relate to three-dimensional (3D) characters and rapidly generating 3D characters from a plurality of 3D source models. In generating the 3D characters, one or more 3D source models may be standardized, applied to a base mesh with material ID assignments, and decomposed to isolate particular polygonal mesh pieces and/or texture map feature selections denoted by the material IDs of the base mesh. The disparate isolated polygonal mesh pieces and/or texture map feature selections may be assembled in a modular fashion to compose unique 3D characters unlike any of those of the one or more 3D models. The 3D characters may be further refined through the addition of features and/or accessories, and may also be processed through machine learning algorithms to further ascertain uniqueness.
1. A method for generating a unique three-dimensional character comprising:
wrapping a plurality of three-dimensional models with a base mesh;
associating one or more of the plurality of three-dimensional models with each of a plurality of IDs on the base mesh, wherein one of the plurality of three-dimensional models is defined as a root three-dimensional model;
creating a plurality of masks on the root three-dimensional model based on the plurality of IDs on the base mesh;
aligning each of the plurality of three-dimensional models in three-dimensional space with the base mesh and the root three-dimensional model; and
based on the ID associations of the one or more of the plurality of three-dimensional models, blending a feature from each of the three-dimensional models onto the root three-dimensional model proportional to the masks created on the root three-dimensional model.
2. The method of claim 1 , wherein the wrapping causes each of the three-dimensional models to have identical polygonal and vertex quantities, ordering, and numbering.
3. The method of claim 1 , wherein each of the plurality of IDs on the base mesh define particular features.
4. The method of claim 1 , wherein the aligning of each of the plurality of three-dimensional models in three-dimensional space with the base mesh and the root three-dimensional model further comprises:
identifying a first set of one or more polygons or vertices on each of the plurality of three-dimensional models and the base mesh; and
based on the first set of one or more polygons or vertices, updating rotational metadata associated with the one or more polygons or vertices on each of the three-dimensional models to mirror the rotational metadata of the one or more polygons or vertices on the base mesh.
5. The method of claim 4 , further comprising:
identifying a second set of one or more polygons or vertices on each of the plurality of three-dimensional models and the root three-dimensional model corresponding to the IDs to which three-dimensional models were assigned;
based on the second set of one or more polygons or vertices, creating bounding boxes on each of three-dimensional models and corresponding bounding boxes on the root three-dimensional model; and
aligning the bounding boxes of each of the three-dimensional models with the corresponding bounding boxes on the root three-dimensional model.
6. The method of claim 1 , wherein blending the feature from each of the three-dimensional models onto the root three-dimensional model further comprises:
multiplying mesh data from each of the plurality of three-dimensional models corresponding to the ID assignment with point attribute data defined by the masks on the root three-dimensional model.
7. The method of claim 1 , further comprising:
executing one or more machine learning algorithms on the three-dimensional character to determine the uniqueness of the three-dimensional character in relation to the plurality of three-dimensional models.
8. One or more non-transitory computer-readable media storing computer media storing instructions that, when executed by a computing device comprising at least one processor and memory, cause the computing device to:
wrap a plurality of three-dimensional models with a base mesh;
associate one or more of the plurality of three-dimensional models with each of a plurality of IDs on the base mesh, wherein one of the plurality of three-dimensional models is defined as a root three-dimensional model;
create a plurality of masks on the root three-dimensional model based on the plurality of IDs on the base mesh;
align each of the plurality of three-dimensional models in three-dimensional space with the base mesh and the root three-dimensional model; and
based on the ID associations of the one or more of the plurality of three-dimensional models, blend a feature from each of the three-dimensional models onto the root three-dimensional model proportional to the masks created on the root three-dimensional model.
9. The one or more non-transitory computer-readable media of claim 8 , wherein the wrapping causes each of the three-dimensional models to have identical polygonal and vertex quantities, ordering, and numbering.
10. The one or more non-transitory computer-readable media of claim 8 , wherein each of the plurality of IDs on the base mesh define particular features.
11. The one or more non-transitory computer-readable media of claim 8 storing further instructions that, when executed by the computing device comprising at least the one processor and memory, cause the computing device to:
identify a first set of one or more polygons or vertices on each of the plurality of three-dimensional models and the base mesh; and
based on the first set of one or more polygons or vertices, update rotational metadata associated with the one or more polygons or vertices on each of the three-dimensional models to mirror the rotational metadata of the one or more polygons or vertices on the base mesh.
12. The one or more non-transitory computer-readable media of claim 11 storing further instructions that, when executed by the computing device comprising at least the one processor and memory, cause the computing device to:
identify a second set of one or more polygons or vertices on each of the plurality of three-dimensional models and the root three-dimensional model corresponding to the IDs to which three-dimensional models were assigned;
based on the second set of one or more polygons or vertices, create bounding boxes on each of three-dimensional models and corresponding bounding boxes on the root three-dimensional model; and
align the bounding boxes of each of the three-dimensional models with the corresponding bounding boxes on the root three-dimensional model.
13. The one or more non-transitory computer-readable media of claim 8 storing further instructions that, when executed by the computing device comprising at least the one processor and memory, cause the computing device to:
multiply mesh data from each of the plurality of three-dimensional models corresponding to the ID assignment with point attribute data defined by the masks on the root three-dimensional model.
14. The one or more non-transitory computer-readable media of claim 8 storing further instructions that, when executed by the computing device comprising at least the one processor and memory, cause the computing device to:
execute one or more machine learning algorithms on the three-dimensional character to determine the uniqueness of the three-dimensional character in relation to the plurality of three-dimensional models.
15. A computing device, comprising:
at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing device to:
wrap a plurality of three-dimensional models of the models with a base mesh;
associate one or more of the plurality of three-dimensional models with each of a plurality of IDs on the base mesh, wherein one of the plurality of three-dimensional models is defined as a root three-dimensional model;
create a plurality of masks on the root three-dimensional model based on the plurality of IDs on the base mesh;
align each of the plurality of three-dimensional models in three-dimensional space with the base mesh and the root three-dimensional model; and
based on the ID associations of the one or more of the plurality of three-dimensional models, blend a feature from each of the three-dimensional models onto the root three-dimensional model proportional to the masks created on the root three-dimensional model.
16. The computing device of claim 15 , wherein the wrapping causes each of the three-dimensional models to have identical polygonal and vertex quantities, ordering, and numbering.
17. The computing device of claim 15 , wherein each of the plurality of IDs on the base mesh define particular features.
18. The computing device of claim 15 , wherein the memory stores further computer-readable instructions that, when executed by the at least one processor, cause the computing device to:
identify a first set of one or more polygons or vertices on each of the plurality of three-dimensional models and the base mesh; and
based on the first set of one or more polygons or vertices, update rotational metadata associated with the one or more polygons or vertices on each of the three-dimensional models to mirror the rotational metadata of the one or more polygons or vertices on the base mesh.
19. The computing device of claim 18 , wherein the memory stores further computer-readable instructions that, when executed by the at least one processor, cause the computing device to:
identify a second set of one or more polygons or vertices on each of the plurality of three-dimensional models and the root three-dimensional model corresponding to the IDs to which three-dimensional models were assigned;
based on the second set of one or more polygons or vertices, create bounding boxes on each of three-dimensional models and corresponding bounding boxes on the root three-dimensional model; and
align the bounding boxes of each of the three-dimensional models with the corresponding bounding boxes on the root three-dimensional model.
20. The computing device of claim 15 , wherein the memory stores further computer-readable instructions that, when executed by the at least one processor, cause the computing device to:
multiply mesh data from each of the plurality of three-dimensional models corresponding to the ID assignment with point attribute data defined by the masks on the root three-dimensional model.